File size: 50,564 Bytes
9c6594c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 |
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied. See the License for the
# specific language governing permissions and limitations
# under the License.
import collections
import warnings
from uuid import UUID
cdef class Scalar(_Weakrefable):
"""
The base class for scalars.
"""
def __init__(self):
raise TypeError("Do not call {}'s constructor directly, use "
"pa.scalar() instead.".format(self.__class__.__name__))
cdef void init(self, const shared_ptr[CScalar]& wrapped):
self.wrapped = wrapped
@staticmethod
cdef wrap(const shared_ptr[CScalar]& wrapped):
cdef:
Scalar self
Type type_id = wrapped.get().type.get().id()
shared_ptr[CDataType] sp_data_type = wrapped.get().type
if type_id == _Type_NA:
return _NULL
if type_id not in _scalar_classes:
raise NotImplementedError(
"Wrapping scalar of type " + frombytes(sp_data_type.get().ToString()))
typ = get_scalar_class_from_type(sp_data_type)
self = typ.__new__(typ)
self.init(wrapped)
return self
cdef inline shared_ptr[CScalar] unwrap(self) nogil:
return self.wrapped
@property
def type(self):
"""
Data type of the Scalar object.
"""
return pyarrow_wrap_data_type(self.wrapped.get().type)
@property
def is_valid(self):
"""
Holds a valid (non-null) value.
"""
return self.wrapped.get().is_valid
def cast(self, object target_type=None, safe=None, options=None, memory_pool=None):
"""
Cast scalar value to another data type.
See :func:`pyarrow.compute.cast` for usage.
Parameters
----------
target_type : DataType, default None
Type to cast scalar to.
safe : boolean, default True
Whether to check for conversion errors such as overflow.
options : CastOptions, default None
Additional checks pass by CastOptions
memory_pool : MemoryPool, optional
memory pool to use for allocations during function execution.
Returns
-------
scalar : A Scalar of the given target data type.
"""
return _pc().cast(self, target_type, safe=safe,
options=options, memory_pool=memory_pool)
def validate(self, *, full=False):
"""
Perform validation checks. An exception is raised if validation fails.
By default only cheap validation checks are run. Pass `full=True`
for thorough validation checks (potentially O(n)).
Parameters
----------
full : bool, default False
If True, run expensive checks, otherwise cheap checks only.
Raises
------
ArrowInvalid
"""
if full:
with nogil:
check_status(self.wrapped.get().ValidateFull())
else:
with nogil:
check_status(self.wrapped.get().Validate())
def __repr__(self):
return '<pyarrow.{}: {!r}>'.format(
self.__class__.__name__, self.as_py()
)
def __str__(self):
return str(self.as_py())
def equals(self, Scalar other not None):
"""
Parameters
----------
other : pyarrow.Scalar
Returns
-------
bool
"""
return self.wrapped.get().Equals(other.unwrap().get()[0])
def __eq__(self, other):
try:
return self.equals(other)
except TypeError:
return NotImplemented
def __hash__(self):
cdef CScalarHash hasher
return hasher(self.wrapped)
def __reduce__(self):
return scalar, (self.as_py(), self.type)
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Python representation.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
The default behavior (`None`), is to convert Arrow Map arrays to
Python association lists (list-of-tuples) in the same order as the
Arrow Map, as in [(key1, value1), (key2, value2), ...].
If 'lossy' or 'strict', convert Arrow Map arrays to native Python dicts.
If 'lossy', whenever duplicate keys are detected, a warning will be printed.
The last seen value of a duplicate key will be in the Python dictionary.
If 'strict', this instead results in an exception being raised when detected.
"""
raise NotImplementedError()
_NULL = NA = None
cdef class NullScalar(Scalar):
"""
Concrete class for null scalars.
"""
def __cinit__(self):
global NA
if NA is not None:
raise RuntimeError('Cannot create multiple NullScalar instances')
self.init(shared_ptr[CScalar](new CNullScalar()))
def __init__(self):
pass
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Python None.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
This parameter is ignored for non-nested Scalars.
"""
return None
_NULL = NA = NullScalar()
cdef class BooleanScalar(Scalar):
"""
Concrete class for boolean scalars.
"""
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Python bool.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
This parameter is ignored for non-nested Scalars.
"""
cdef CBooleanScalar* sp = <CBooleanScalar*> self.wrapped.get()
return sp.value if sp.is_valid else None
cdef class UInt8Scalar(Scalar):
"""
Concrete class for uint8 scalars.
"""
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Python int.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
This parameter is ignored for non-nested Scalars.
"""
cdef CUInt8Scalar* sp = <CUInt8Scalar*> self.wrapped.get()
return sp.value if sp.is_valid else None
cdef class Int8Scalar(Scalar):
"""
Concrete class for int8 scalars.
"""
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Python int.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
This parameter is ignored for non-nested Scalars.
"""
cdef CInt8Scalar* sp = <CInt8Scalar*> self.wrapped.get()
return sp.value if sp.is_valid else None
cdef class UInt16Scalar(Scalar):
"""
Concrete class for uint16 scalars.
"""
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Python int.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
This parameter is ignored for non-nested Scalars.
"""
cdef CUInt16Scalar* sp = <CUInt16Scalar*> self.wrapped.get()
return sp.value if sp.is_valid else None
cdef class Int16Scalar(Scalar):
"""
Concrete class for int16 scalars.
"""
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Python int.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
This parameter is ignored for non-nested Scalars.
"""
cdef CInt16Scalar* sp = <CInt16Scalar*> self.wrapped.get()
return sp.value if sp.is_valid else None
cdef class UInt32Scalar(Scalar):
"""
Concrete class for uint32 scalars.
"""
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Python int.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
This parameter is ignored for non-nested Scalars.
"""
cdef CUInt32Scalar* sp = <CUInt32Scalar*> self.wrapped.get()
return sp.value if sp.is_valid else None
cdef class Int32Scalar(Scalar):
"""
Concrete class for int32 scalars.
"""
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Python int.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
This parameter is ignored for non-nested Scalars.
"""
cdef CInt32Scalar* sp = <CInt32Scalar*> self.wrapped.get()
return sp.value if sp.is_valid else None
cdef class UInt64Scalar(Scalar):
"""
Concrete class for uint64 scalars.
"""
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Python int.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
This parameter is ignored for non-nested Scalars.
"""
cdef CUInt64Scalar* sp = <CUInt64Scalar*> self.wrapped.get()
return sp.value if sp.is_valid else None
cdef class Int64Scalar(Scalar):
"""
Concrete class for int64 scalars.
"""
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Python int.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
This parameter is ignored for non-nested Scalars.
"""
cdef CInt64Scalar* sp = <CInt64Scalar*> self.wrapped.get()
return sp.value if sp.is_valid else None
cdef class HalfFloatScalar(Scalar):
"""
Concrete class for float scalars.
"""
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Python float.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
This parameter is ignored for non-nested Scalars.
"""
cdef CHalfFloatScalar* sp = <CHalfFloatScalar*> self.wrapped.get()
return PyHalf_FromHalf(sp.value) if sp.is_valid else None
cdef class FloatScalar(Scalar):
"""
Concrete class for float scalars.
"""
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Python float.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
This parameter is ignored for non-nested Scalars.
"""
cdef CFloatScalar* sp = <CFloatScalar*> self.wrapped.get()
return sp.value if sp.is_valid else None
cdef class DoubleScalar(Scalar):
"""
Concrete class for double scalars.
"""
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Python float.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
This parameter is ignored for non-nested Scalars.
"""
cdef CDoubleScalar* sp = <CDoubleScalar*> self.wrapped.get()
return sp.value if sp.is_valid else None
cdef class Decimal32Scalar(Scalar):
"""
Concrete class for decimal32 scalars.
"""
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Python Decimal.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
This parameter is ignored for non-nested Scalars.
"""
cdef:
CDecimal32Scalar* sp = <CDecimal32Scalar*> self.wrapped.get()
CDecimal32Type* dtype = <CDecimal32Type*> sp.type.get()
if sp.is_valid:
return _pydecimal.Decimal(
frombytes(sp.value.ToString(dtype.scale()))
)
else:
return None
cdef class Decimal64Scalar(Scalar):
"""
Concrete class for decimal64 scalars.
"""
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Python Decimal.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
This parameter is ignored for non-nested Scalars.
"""
cdef:
CDecimal64Scalar* sp = <CDecimal64Scalar*> self.wrapped.get()
CDecimal64Type* dtype = <CDecimal64Type*> sp.type.get()
if sp.is_valid:
return _pydecimal.Decimal(
frombytes(sp.value.ToString(dtype.scale()))
)
else:
return None
cdef class Decimal128Scalar(Scalar):
"""
Concrete class for decimal128 scalars.
"""
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Python Decimal.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
This parameter is ignored for non-nested Scalars.
"""
cdef:
CDecimal128Scalar* sp = <CDecimal128Scalar*> self.wrapped.get()
CDecimal128Type* dtype = <CDecimal128Type*> sp.type.get()
if sp.is_valid:
return _pydecimal.Decimal(
frombytes(sp.value.ToString(dtype.scale()))
)
else:
return None
cdef class Decimal256Scalar(Scalar):
"""
Concrete class for decimal256 scalars.
"""
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Python Decimal.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
This parameter is ignored for non-nested Scalars.
"""
cdef:
CDecimal256Scalar* sp = <CDecimal256Scalar*> self.wrapped.get()
CDecimal256Type* dtype = <CDecimal256Type*> sp.type.get()
if sp.is_valid:
return _pydecimal.Decimal(
frombytes(sp.value.ToString(dtype.scale()))
)
else:
return None
cdef class Date32Scalar(Scalar):
"""
Concrete class for date32 scalars.
"""
@property
def value(self):
cdef CDate32Scalar* sp = <CDate32Scalar*> self.wrapped.get()
return sp.value if sp.is_valid else None
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Python datetime.datetime instance.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
This parameter is ignored for non-nested Scalars.
"""
cdef CDate32Scalar* sp = <CDate32Scalar*> self.wrapped.get()
if sp.is_valid:
# shift to seconds since epoch
return (
datetime.date(1970, 1, 1) + datetime.timedelta(days=sp.value)
)
else:
return None
cdef class Date64Scalar(Scalar):
"""
Concrete class for date64 scalars.
"""
@property
def value(self):
cdef CDate64Scalar* sp = <CDate64Scalar*> self.wrapped.get()
return sp.value if sp.is_valid else None
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Python datetime.datetime instance.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
This parameter is ignored for non-nested Scalars.
"""
cdef CDate64Scalar* sp = <CDate64Scalar*> self.wrapped.get()
if sp.is_valid:
return (
datetime.date(1970, 1, 1) +
datetime.timedelta(days=sp.value / 86400000)
)
else:
return None
def _datetime_from_int(int64_t value, TimeUnit unit, tzinfo=None):
if unit == TimeUnit_SECOND:
delta = datetime.timedelta(seconds=value)
elif unit == TimeUnit_MILLI:
delta = datetime.timedelta(milliseconds=value)
elif unit == TimeUnit_MICRO:
delta = datetime.timedelta(microseconds=value)
else:
# TimeUnit_NANO: prefer pandas timestamps if available
if _pandas_api.have_pandas:
return _pandas_api.pd.Timestamp(value, tz=tzinfo, unit='ns')
# otherwise safely truncate to microsecond resolution datetime
if value % 1000 != 0:
raise ValueError(
"Nanosecond resolution temporal type {} is not safely "
"convertible to microseconds to convert to datetime.datetime. "
"Install pandas to return as Timestamp with nanosecond "
"support or access the .value attribute.".format(value)
)
delta = datetime.timedelta(microseconds=value // 1000)
dt = datetime.datetime(1970, 1, 1) + delta
# adjust timezone if set to the datatype
if tzinfo is not None:
dt = dt.replace(tzinfo=datetime.timezone.utc).astimezone(tzinfo)
return dt
cdef class Time32Scalar(Scalar):
"""
Concrete class for time32 scalars.
"""
@property
def value(self):
cdef CTime32Scalar* sp = <CTime32Scalar*> self.wrapped.get()
return sp.value if sp.is_valid else None
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Python datetime.timedelta instance.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
This parameter is ignored for non-nested Scalars.
"""
cdef:
CTime32Scalar* sp = <CTime32Scalar*> self.wrapped.get()
CTime32Type* dtype = <CTime32Type*> sp.type.get()
if sp.is_valid:
return _datetime_from_int(sp.value, unit=dtype.unit()).time()
else:
return None
cdef class Time64Scalar(Scalar):
"""
Concrete class for time64 scalars.
"""
@property
def value(self):
cdef CTime64Scalar* sp = <CTime64Scalar*> self.wrapped.get()
return sp.value if sp.is_valid else None
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Python datetime.timedelta instance.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
This parameter is ignored for non-nested Scalars.
"""
cdef:
CTime64Scalar* sp = <CTime64Scalar*> self.wrapped.get()
CTime64Type* dtype = <CTime64Type*> sp.type.get()
if sp.is_valid:
return _datetime_from_int(sp.value, unit=dtype.unit()).time()
else:
return None
cdef class TimestampScalar(Scalar):
"""
Concrete class for timestamp scalars.
"""
@property
def value(self):
cdef CTimestampScalar* sp = <CTimestampScalar*> self.wrapped.get()
return sp.value if sp.is_valid else None
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Pandas Timestamp instance (if units are
nanoseconds and pandas is available), otherwise as a Python
datetime.datetime instance.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
This parameter is ignored for non-nested Scalars.
"""
cdef:
CTimestampScalar* sp = <CTimestampScalar*> self.wrapped.get()
CTimestampType* dtype = <CTimestampType*> sp.type.get()
if not sp.is_valid:
return None
if not dtype.timezone().empty():
tzinfo = string_to_tzinfo(frombytes(dtype.timezone()))
else:
tzinfo = None
return _datetime_from_int(sp.value, unit=dtype.unit(), tzinfo=tzinfo)
def __repr__(self):
"""
Return the representation of TimestampScalar using `strftime` to avoid
original repr datetime values being out of range.
"""
cdef:
CTimestampScalar* sp = <CTimestampScalar*> self.wrapped.get()
CTimestampType* dtype = <CTimestampType*> sp.type.get()
if not dtype.timezone().empty():
type_format = str(_pc().strftime(self, format="%Y-%m-%dT%H:%M:%S%z"))
else:
type_format = str(_pc().strftime(self))
return '<pyarrow.{}: {!r}>'.format(
self.__class__.__name__, type_format
)
cdef class DurationScalar(Scalar):
"""
Concrete class for duration scalars.
"""
@property
def value(self):
cdef CDurationScalar* sp = <CDurationScalar*> self.wrapped.get()
return sp.value if sp.is_valid else None
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Pandas Timedelta instance (if units are
nanoseconds and pandas is available), otherwise as a Python
datetime.timedelta instance.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
This parameter is ignored for non-nested Scalars.
"""
cdef:
CDurationScalar* sp = <CDurationScalar*> self.wrapped.get()
CDurationType* dtype = <CDurationType*> sp.type.get()
TimeUnit unit = dtype.unit()
if not sp.is_valid:
return None
if unit == TimeUnit_SECOND:
return datetime.timedelta(seconds=sp.value)
elif unit == TimeUnit_MILLI:
return datetime.timedelta(milliseconds=sp.value)
elif unit == TimeUnit_MICRO:
return datetime.timedelta(microseconds=sp.value)
else:
# TimeUnit_NANO: prefer pandas timestamps if available
if _pandas_api.have_pandas:
return _pandas_api.pd.Timedelta(sp.value, unit='ns')
# otherwise safely truncate to microsecond resolution timedelta
if sp.value % 1000 != 0:
raise ValueError(
"Nanosecond duration {} is not safely convertible to "
"microseconds to convert to datetime.timedelta. Install "
"pandas to return as Timedelta with nanosecond support or "
"access the .value attribute.".format(sp.value)
)
return datetime.timedelta(microseconds=sp.value // 1000)
cdef class MonthDayNanoIntervalScalar(Scalar):
"""
Concrete class for month, day, nanosecond interval scalars.
"""
@property
def value(self):
"""
Same as self.as_py()
"""
return self.as_py()
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a pyarrow.MonthDayNano.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
This parameter is ignored for non-nested Scalars.
"""
cdef:
PyObject* val
CMonthDayNanoIntervalScalar* scalar
scalar = <CMonthDayNanoIntervalScalar*>self.wrapped.get()
val = GetResultValue(MonthDayNanoIntervalScalarToPyObject(
deref(scalar)))
return PyObject_to_object(val)
cdef class BinaryScalar(Scalar):
"""
Concrete class for binary-like scalars.
"""
def as_buffer(self):
"""
Return a view over this value as a Buffer object.
"""
cdef CBaseBinaryScalar* sp = <CBaseBinaryScalar*> self.wrapped.get()
return pyarrow_wrap_buffer(sp.value) if sp.is_valid else None
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Python bytes.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
This parameter is ignored for non-nested Scalars.
"""
buffer = self.as_buffer()
return None if buffer is None else buffer.to_pybytes()
cdef class LargeBinaryScalar(BinaryScalar):
pass
cdef class FixedSizeBinaryScalar(BinaryScalar):
pass
cdef class StringScalar(BinaryScalar):
"""
Concrete class for string-like (utf8) scalars.
"""
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Python string.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
This parameter is ignored for non-nested Scalars.
"""
buffer = self.as_buffer()
return None if buffer is None else str(buffer, 'utf8')
cdef class LargeStringScalar(StringScalar):
pass
cdef class BinaryViewScalar(BinaryScalar):
pass
cdef class StringViewScalar(StringScalar):
pass
cdef class ListScalar(Scalar):
"""
Concrete class for list-like scalars.
"""
@property
def values(self):
cdef CBaseListScalar* sp = <CBaseListScalar*> self.wrapped.get()
if sp.is_valid:
return pyarrow_wrap_array(sp.value)
else:
return None
def __len__(self):
"""
Return the number of values.
"""
return len(self.values)
def __getitem__(self, i):
"""
Return the value at the given index.
"""
return self.values[_normalize_index(i, len(self))]
def __iter__(self):
"""
Iterate over this element's values.
"""
return iter(self.values)
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Python list.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
The default behavior (`None`), is to convert Arrow Map arrays to
Python association lists (list-of-tuples) in the same order as the
Arrow Map, as in [(key1, value1), (key2, value2), ...].
If 'lossy' or 'strict', convert Arrow Map arrays to native Python dicts.
If 'lossy', whenever duplicate keys are detected, a warning will be printed.
The last seen value of a duplicate key will be in the Python dictionary.
If 'strict', this instead results in an exception being raised when detected.
"""
arr = self.values
return None if arr is None else arr.to_pylist(maps_as_pydicts=maps_as_pydicts)
cdef class FixedSizeListScalar(ListScalar):
pass
cdef class LargeListScalar(ListScalar):
pass
cdef class ListViewScalar(ListScalar):
pass
cdef class LargeListViewScalar(ListScalar):
pass
cdef class StructScalar(Scalar, collections.abc.Mapping):
"""
Concrete class for struct scalars.
"""
def __len__(self):
cdef CStructScalar* sp = <CStructScalar*> self.wrapped.get()
return sp.value.size()
def __iter__(self):
cdef:
CStructScalar* sp = <CStructScalar*> self.wrapped.get()
CStructType* dtype = <CStructType*> sp.type.get()
vector[shared_ptr[CField]] fields = dtype.fields()
for i in range(dtype.num_fields()):
yield frombytes(fields[i].get().name())
def items(self):
return ((key, self[i]) for i, key in enumerate(self))
def __contains__(self, key):
return key in list(self)
def __getitem__(self, key):
"""
Return the child value for the given field.
Parameters
----------
index : Union[int, str]
Index / position or name of the field.
Returns
-------
result : Scalar
"""
cdef:
CFieldRef ref
CStructScalar* sp = <CStructScalar*> self.wrapped.get()
if isinstance(key, (bytes, str)):
ref = CFieldRef(<c_string> tobytes(key))
elif isinstance(key, int):
ref = CFieldRef(<int> key)
else:
raise TypeError('Expected integer or string index')
try:
return Scalar.wrap(GetResultValue(sp.field(ref)))
except ArrowInvalid as exc:
if isinstance(key, int):
raise IndexError(key) from exc
else:
raise KeyError(key) from exc
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Python dict.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
The default behavior (`None`), is to convert Arrow Map arrays to
Python association lists (list-of-tuples) in the same order as the
Arrow Map, as in [(key1, value1), (key2, value2), ...].
If 'lossy' or 'strict', convert Arrow Map arrays to native Python dicts.
If 'lossy', whenever duplicate keys are detected, a warning will be printed.
The last seen value of a duplicate key will be in the Python dictionary.
If 'strict', this instead results in an exception being raised when detected.
"""
if self.is_valid:
try:
return {k: self[k].as_py(maps_as_pydicts=maps_as_pydicts) for k in self.keys()}
except KeyError:
raise ValueError(
"Converting to Python dictionary is not supported when "
"duplicate field names are present")
else:
return None
def _as_py_tuple(self):
# a version that returns a tuple instead of dict to support repr/str
# with the presence of duplicate field names
if self.is_valid:
return [(key, self[i].as_py()) for i, key in enumerate(self)]
else:
return None
def __repr__(self):
return '<pyarrow.{}: {!r}>'.format(
self.__class__.__name__, self._as_py_tuple()
)
def __str__(self):
return str(self._as_py_tuple())
cdef class MapScalar(ListScalar):
"""
Concrete class for map scalars.
"""
def __getitem__(self, i):
"""
Return the value at the given index.
"""
arr = self.values
if arr is None:
raise IndexError(i)
dct = arr[_normalize_index(i, len(arr))]
return (dct[self.type.key_field.name], dct[self.type.item_field.name])
def __iter__(self):
"""
Iterate over this element's values.
"""
arr = self.values
if arr is None:
return
for k, v in zip(arr.field(self.type.key_field.name), arr.field(self.type.item_field.name)):
yield (k.as_py(), v.as_py())
def as_py(self, *, maps_as_pydicts=None):
"""
Return this value as a Python list or dict, depending on 'maps_as_pydicts'.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
The default behavior (`None`), is to convert Arrow Map arrays to
Python association lists (list-of-tuples) in the same order as the
Arrow Map, as in [(key1, value1), (key2, value2), ...].
If 'lossy' or 'strict', convert Arrow Map arrays to native Python dicts.
If 'lossy', whenever duplicate keys are detected, a warning will be printed.
The last seen value of a duplicate key will be in the Python dictionary.
If 'strict', this instead results in an exception being raised when detected.
"""
if maps_as_pydicts not in (None, "lossy", "strict"):
raise ValueError(
"Invalid value for 'maps_as_pydicts': "
+ "valid values are 'lossy', 'strict' or `None` (default). "
+ f"Received {maps_as_pydicts!r}."
)
if not self.is_valid:
return None
if not maps_as_pydicts:
return list(self)
result_dict = {}
for key, value in self:
if key in result_dict:
if maps_as_pydicts == "strict":
raise KeyError(
"Converting to Python dictionary is not supported in strict mode "
f"when duplicate keys are present (duplicate key was '{key}')."
)
else:
warnings.warn(
f"Encountered key '{key}' which was already encountered.")
result_dict[key] = value
return result_dict
cdef class DictionaryScalar(Scalar):
"""
Concrete class for dictionary-encoded scalars.
"""
@staticmethod
def _reconstruct(type, is_valid, index, dictionary):
cdef:
CDictionaryScalarIndexAndDictionary value
shared_ptr[CDictionaryScalar] wrapped
DataType type_
Scalar index_
Array dictionary_
type_ = ensure_type(type, allow_none=False)
if not isinstance(type_, DictionaryType):
raise TypeError('Must pass a DictionaryType instance')
if isinstance(index, Scalar):
if not index.type.equals(type.index_type):
raise TypeError("The Scalar value passed as index must have "
"identical type to the dictionary type's "
"index_type")
index_ = index
else:
index_ = scalar(index, type=type_.index_type)
if isinstance(dictionary, Array):
if not dictionary.type.equals(type.value_type):
raise TypeError("The Array passed as dictionary must have "
"identical type to the dictionary type's "
"value_type")
dictionary_ = dictionary
else:
dictionary_ = array(dictionary, type=type_.value_type)
value.index = pyarrow_unwrap_scalar(index_)
value.dictionary = pyarrow_unwrap_array(dictionary_)
wrapped = make_shared[CDictionaryScalar](
value, pyarrow_unwrap_data_type(type_), <c_bool>(is_valid)
)
return Scalar.wrap(<shared_ptr[CScalar]> wrapped)
def __reduce__(self):
return DictionaryScalar._reconstruct, (
self.type, self.is_valid, self.index, self.dictionary
)
@property
def index(self):
"""
Return this value's underlying index as a scalar.
"""
cdef CDictionaryScalar* sp = <CDictionaryScalar*> self.wrapped.get()
return Scalar.wrap(sp.value.index)
@property
def value(self):
"""
Return the encoded value as a scalar.
"""
cdef CDictionaryScalar* sp = <CDictionaryScalar*> self.wrapped.get()
return Scalar.wrap(GetResultValue(sp.GetEncodedValue()))
@property
def dictionary(self):
cdef CDictionaryScalar* sp = <CDictionaryScalar*> self.wrapped.get()
return pyarrow_wrap_array(sp.value.dictionary)
def as_py(self, *, maps_as_pydicts=None):
"""
Return this encoded value as a Python object.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
The default behavior (`None`), is to convert Arrow Map arrays to
Python association lists (list-of-tuples) in the same order as the
Arrow Map, as in [(key1, value1), (key2, value2), ...].
If 'lossy' or 'strict', convert Arrow Map arrays to native Python dicts.
If 'lossy', whenever duplicate keys are detected, a warning will be printed.
The last seen value of a duplicate key will be in the Python dictionary.
If 'strict', this instead results in an exception being raised when detected.
"""
return self.value.as_py(maps_as_pydicts=maps_as_pydicts) if self.is_valid else None
cdef class RunEndEncodedScalar(Scalar):
"""
Concrete class for RunEndEncoded scalars.
"""
@property
def value(self):
"""
Return underlying value as a scalar.
"""
cdef CRunEndEncodedScalar* sp = <CRunEndEncodedScalar*> self.wrapped.get()
return Scalar.wrap(sp.value)
def as_py(self, *, maps_as_pydicts=None):
"""
Return underlying value as a Python object.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
The default behavior (`None`), is to convert Arrow Map arrays to
Python association lists (list-of-tuples) in the same order as the
Arrow Map, as in [(key1, value1), (key2, value2), ...].
If 'lossy' or 'strict', convert Arrow Map arrays to native Python dicts.
If 'lossy', whenever duplicate keys are detected, a warning will be printed.
The last seen value of a duplicate key will be in the Python dictionary.
If 'strict', this instead results in an exception being raised when detected.
"""
return self.value.as_py(maps_as_pydicts=maps_as_pydicts)
cdef class UnionScalar(Scalar):
"""
Concrete class for Union scalars.
"""
@property
def value(self):
"""
Return underlying value as a scalar.
"""
cdef CSparseUnionScalar* sp
cdef CDenseUnionScalar* dp
if self.type.id == _Type_SPARSE_UNION:
sp = <CSparseUnionScalar*> self.wrapped.get()
return Scalar.wrap(sp.value[sp.child_id]) if sp.is_valid else None
else:
dp = <CDenseUnionScalar*> self.wrapped.get()
return Scalar.wrap(dp.value) if dp.is_valid else None
def as_py(self, *, maps_as_pydicts=None):
"""
Return underlying value as a Python object.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
The default behavior (`None`), is to convert Arrow Map arrays to
Python association lists (list-of-tuples) in the same order as the
Arrow Map, as in [(key1, value1), (key2, value2), ...].
If 'lossy' or 'strict', convert Arrow Map arrays to native Python dicts.
If 'lossy', whenever duplicate keys are detected, a warning will be printed.
The last seen value of a duplicate key will be in the Python dictionary.
If 'strict', this instead results in an exception being raised when detected.
"""
value = self.value
return None if value is None else value.as_py(maps_as_pydicts=maps_as_pydicts)
@property
def type_code(self):
"""
Return the union type code for this scalar.
"""
cdef CUnionScalar* sp = <CUnionScalar*> self.wrapped.get()
return sp.type_code
cdef class ExtensionScalar(Scalar):
"""
Concrete class for Extension scalars.
"""
@property
def value(self):
"""
Return storage value as a scalar.
"""
cdef CExtensionScalar* sp = <CExtensionScalar*> self.wrapped.get()
return Scalar.wrap(sp.value) if sp.is_valid else None
def as_py(self, *, maps_as_pydicts=None):
"""
Return this scalar as a Python object.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
The default behavior (`None`), is to convert Arrow Map arrays to
Python association lists (list-of-tuples) in the same order as the
Arrow Map, as in [(key1, value1), (key2, value2), ...].
If 'lossy' or 'strict', convert Arrow Map arrays to native Python dicts.
If 'lossy', whenever duplicate keys are detected, a warning will be printed.
The last seen value of a duplicate key will be in the Python dictionary.
If 'strict', this instead results in an exception being raised when detected.
"""
return None if self.value is None else self.value.as_py(maps_as_pydicts=maps_as_pydicts)
@staticmethod
def from_storage(BaseExtensionType typ, value):
"""
Construct ExtensionScalar from type and storage value.
Parameters
----------
typ : DataType
The extension type for the result scalar.
value : object
The storage value for the result scalar.
Returns
-------
ext_scalar : ExtensionScalar
"""
cdef:
shared_ptr[CExtensionScalar] sp_scalar
shared_ptr[CScalar] sp_storage
CExtensionScalar* ext_scalar
if value is None:
storage = None
elif isinstance(value, Scalar):
if value.type != typ.storage_type:
raise TypeError("Incompatible storage type {0} "
"for extension type {1}"
.format(value.type, typ))
storage = value
else:
storage = scalar(value, typ.storage_type)
cdef c_bool is_valid = storage is not None and storage.is_valid
if is_valid:
sp_storage = pyarrow_unwrap_scalar(storage)
else:
sp_storage = MakeNullScalar((<DataType> typ.storage_type).sp_type)
sp_scalar = make_shared[CExtensionScalar](sp_storage, typ.sp_type,
is_valid)
with nogil:
check_status(sp_scalar.get().Validate())
return pyarrow_wrap_scalar(<shared_ptr[CScalar]> sp_scalar)
class JsonScalar(ExtensionScalar):
"""
Concrete class for JSON extension scalar.
"""
class UuidScalar(ExtensionScalar):
"""
Concrete class for Uuid extension scalar.
"""
def as_py(self, *, maps_as_pydicts=None):
"""
Return this scalar as a Python UUID.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
This parameter is ignored for non-nested Scalars.
"""
return None if self.value is None else UUID(bytes=self.value.as_py())
cdef class FixedShapeTensorScalar(ExtensionScalar):
"""
Concrete class for fixed shape tensor extension scalar.
"""
def to_numpy(self):
"""
Convert fixed shape tensor scalar to a numpy.ndarray.
The resulting ndarray's shape matches the permuted shape of the
fixed shape tensor scalar.
The conversion is zero-copy.
Returns
-------
numpy.ndarray
"""
return self.to_tensor().to_numpy()
def to_tensor(self):
"""
Convert fixed shape tensor extension scalar to a pyarrow.Tensor, using shape
and strides derived from corresponding FixedShapeTensorType.
The conversion is zero-copy.
Returns
-------
pyarrow.Tensor
Tensor represented stored in FixedShapeTensorScalar.
"""
cdef:
CFixedShapeTensorType* c_type = static_pointer_cast[CFixedShapeTensorType, CDataType](
self.wrapped.get().type).get()
shared_ptr[CExtensionScalar] scalar = static_pointer_cast[CExtensionScalar, CScalar](self.wrapped)
shared_ptr[CTensor] ctensor
with nogil:
ctensor = GetResultValue(c_type.MakeTensor(scalar))
return pyarrow_wrap_tensor(ctensor)
cdef class OpaqueScalar(ExtensionScalar):
"""
Concrete class for opaque extension scalar.
"""
cdef class Bool8Scalar(ExtensionScalar):
"""
Concrete class for bool8 extension scalar.
"""
def as_py(self, *, maps_as_pydicts=None):
"""
Return this scalar as a Python object.
Parameters
----------
maps_as_pydicts : str, optional, default `None`
Valid values are `None`, 'lossy', or 'strict'.
This parameter is ignored for non-nested Scalars.
"""
py_val = super().as_py()
return None if py_val is None else py_val != 0
cdef dict _scalar_classes = {
_Type_BOOL: BooleanScalar,
_Type_UINT8: UInt8Scalar,
_Type_UINT16: UInt16Scalar,
_Type_UINT32: UInt32Scalar,
_Type_UINT64: UInt64Scalar,
_Type_INT8: Int8Scalar,
_Type_INT16: Int16Scalar,
_Type_INT32: Int32Scalar,
_Type_INT64: Int64Scalar,
_Type_HALF_FLOAT: HalfFloatScalar,
_Type_FLOAT: FloatScalar,
_Type_DOUBLE: DoubleScalar,
_Type_DECIMAL32: Decimal32Scalar,
_Type_DECIMAL64: Decimal64Scalar,
_Type_DECIMAL128: Decimal128Scalar,
_Type_DECIMAL256: Decimal256Scalar,
_Type_DATE32: Date32Scalar,
_Type_DATE64: Date64Scalar,
_Type_TIME32: Time32Scalar,
_Type_TIME64: Time64Scalar,
_Type_TIMESTAMP: TimestampScalar,
_Type_DURATION: DurationScalar,
_Type_BINARY: BinaryScalar,
_Type_LARGE_BINARY: LargeBinaryScalar,
_Type_FIXED_SIZE_BINARY: FixedSizeBinaryScalar,
_Type_BINARY_VIEW: BinaryViewScalar,
_Type_STRING: StringScalar,
_Type_LARGE_STRING: LargeStringScalar,
_Type_STRING_VIEW: StringViewScalar,
_Type_LIST: ListScalar,
_Type_LARGE_LIST: LargeListScalar,
_Type_FIXED_SIZE_LIST: FixedSizeListScalar,
_Type_LIST_VIEW: ListViewScalar,
_Type_LARGE_LIST_VIEW: LargeListViewScalar,
_Type_STRUCT: StructScalar,
_Type_MAP: MapScalar,
_Type_DICTIONARY: DictionaryScalar,
_Type_RUN_END_ENCODED: RunEndEncodedScalar,
_Type_SPARSE_UNION: UnionScalar,
_Type_DENSE_UNION: UnionScalar,
_Type_INTERVAL_MONTH_DAY_NANO: MonthDayNanoIntervalScalar,
_Type_EXTENSION: ExtensionScalar,
}
cdef object get_scalar_class_from_type(
const shared_ptr[CDataType]& sp_data_type):
cdef CDataType* data_type = sp_data_type.get()
if data_type == NULL:
raise ValueError('Scalar data type was NULL')
if data_type.id() == _Type_EXTENSION:
py_ext_data_type = pyarrow_wrap_data_type(sp_data_type)
return py_ext_data_type.__arrow_ext_scalar_class__()
else:
return _scalar_classes[data_type.id()]
def scalar(value, type=None, *, from_pandas=None, MemoryPool memory_pool=None):
"""
Create a pyarrow.Scalar instance from a Python object.
Parameters
----------
value : Any
Python object coercible to arrow's type system.
type : pyarrow.DataType
Explicit type to attempt to coerce to, otherwise will be inferred from
the value.
from_pandas : bool, default None
Use pandas's semantics for inferring nulls from values in
ndarray-like data. Defaults to False if not passed explicitly by user,
or True if a pandas object is passed in.
memory_pool : pyarrow.MemoryPool, optional
If not passed, will allocate memory from the currently-set default
memory pool.
Returns
-------
scalar : pyarrow.Scalar
Examples
--------
>>> import pyarrow as pa
>>> pa.scalar(42)
<pyarrow.Int64Scalar: 42>
>>> pa.scalar("string")
<pyarrow.StringScalar: 'string'>
>>> pa.scalar([1, 2])
<pyarrow.ListScalar: [1, 2]>
>>> pa.scalar([1, 2], type=pa.list_(pa.int16()))
<pyarrow.ListScalar: [1, 2]>
"""
cdef:
DataType ty
PyConversionOptions options
shared_ptr[CScalar] scalar
shared_ptr[CArray] array
shared_ptr[CChunkedArray] chunked
bint is_pandas_object = False
CMemoryPool* pool
type = ensure_type(type, allow_none=True)
pool = maybe_unbox_memory_pool(memory_pool)
extension_type = None
if type is not None and type.id == _Type_EXTENSION:
extension_type = type
type = type.storage_type
if _is_array_like(value):
value = get_values(value, &is_pandas_object)
options.size = 1
if type is not None:
ty = ensure_type(type)
options.type = ty.sp_type
if from_pandas is None:
options.from_pandas = is_pandas_object
else:
options.from_pandas = from_pandas
value = [value]
with nogil:
chunked = GetResultValue(ConvertPySequence(value, None, options, pool))
# get the first chunk
assert chunked.get().num_chunks() == 1
array = chunked.get().chunk(0)
# retrieve the scalar from the first position
scalar = GetResultValue(array.get().GetScalar(0))
result = Scalar.wrap(scalar)
if extension_type is not None:
result = ExtensionScalar.from_storage(extension_type, result)
return result
|